Scribd
Upload
9 views1 page

Machine Learning

Uploaded by

merrtatay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
9 views1 page

Machine Learning

Uploaded by

merrtatay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 1

melbourne_file_path = '../input/melbourne-housing-snapshot/melb_data.

csv'
melbourne_data = pd.read_csv(melbourne_file_path)

filtered_melbourne_data = melbourne_data.dropna(axis=0)

y = filtered_melbourne_data.Price
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea',
'YearBuilt', 'Lattitude', 'Longtitude']
X = filtered_melbourne_data[melbourne_features]

from sklearn.model_selection import train_test_split

train_X, val_X, train_y, val_y = train_test_split(X, y,random_state = 0)


from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeRegressor

def get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y):


model = DecisionTreeRegressor(max_leaf_nodes=max_leaf_nodes, random_state=0)
model.fit(train_X, train_y)
preds_val = model.predict(val_X)
mae = mean_absolute_error(val_y, preds_val)
return(mae)
for max_leaf_nodes in [5, 50, 500, 5000]:
my_mae = get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y)
print("Max leaf nodes: %d \t\t Mean Absolute Error: %d" %(max_leaf_nodes,
my_mae))

///////////////////////////////////////////////////////////////////////////////////
//////////

categorical_cols = [cname for cname in X_train_full.columns if


X_train_full[cname].nunique() < 10 and
X_train_full[cname].dtype == "object"]

You might also like